Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 304
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate legal status or citizenship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cer
    -0.68
    KEY
    -0.68
    then
    -0.68
    chie
    -0.65
    ck
    -0.62
    LC
    -0.61
    dt
    -0.60
    call
    -0.60
    key
    -0.59
    キ
    -0.58
    POSITIVE LOGITS
    osuke
    0.74
    olitan
    0.69
    ylum
    0.66
    agher
    0.66
    inous
    0.64
     neglig
    0.63
     Released
    0.62
    uana
    0.61
    endon
    0.61
    dies
    0.61
    Activations Density 0.248%

    No Known Activations